Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1268189 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4867. Min Act: -0.0000

Data Index: 154010 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4167. Min Act: -0.0000

Data Index: 826409 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1035303 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1391549 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1434548 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3609. Min Act: -0.0000

Data Index: 805133 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3094. Min Act: -0.0000

Data Index: 886288 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1673447 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1615736 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2984. Min Act: -0.0000

Data Index: 832634 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2880. Min Act: -0.0000

Data Index: 665553 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2936. Min Act: -0.0000

Data Index: 402733 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1750524 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1410277 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2671. Min Act: -0.0000

Data Index: 543383 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2715. Min Act: -0.0000

Data Index: 467897 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2700. Min Act: -0.0000

Data Index: 557524 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1242662 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.2497. Min Act: -0.0000

Data Index: 958988 (The Pile)

Max Activating Token Index: 135